Low-Power IoT Person Detector For Battery-Powered Edge AI Applications 


It brings human-figure detection to IoT image and video at just 0.7 mJ per inference – a 100 times improvement

By leveraging Aizip’s Visual Wake Words (VWW) model, Maxim Integrated’s low-power, neural-network microcontroller, the MAX78000 can now execute AI inferences at less than 1/100th the energy of conventional software solutions, improving run-time for battery-powered edge AI applications. 

The low-power network provides longer operation for battery-powered IoT systems that require human-presence detection, including building energy management and smart security cameras.

Key Advantages

Extended Battery Life: Efficient AI model and low power microcontroller system-on-chip (SoC) reduce inference energy to 0.7 mJ, allowing 13 million inferences from a single AA/LR6 battery.

Cost-Effective Intelligence at the Edge: Extreme model compression enables accurate smart vision with a memory-constrained, low-cost AI accelerated microcontroller and budget-friendly image sensors.

The MAX78000 microcontroller and MAX78000EVKIT# evaluation kit are available now at Maxim Integrated’s website and through authorised distributors. AIV DNN series models, tools and services are available directly from Aizip.






Source link

We will be happy to hear your thoughts

Leave a reply

My Blog
Logo
Reset Password
Compare items
  • Total (0)
Compare
0